LiCQA : A Lightweight Complex Question Answering System

TL;DR

LiCQA is an unsupervised, corpus-based question answering system designed for complex questions, demonstrating superior efficiency and effectiveness compared to recent neural and knowledge graph-based QA systems.

Contribution

The paper introduces LiCQA, a novel unsupervised QA model that relies on corpus evidence, reducing computational costs and training data needs for complex question answering.

Findings

LiCQA outperforms state-of-the-art systems on benchmark datasets.

LiCQA achieves significant reduction in latency.

LiCQA demonstrates effective handling of complex questions without supervised training.

Abstract

Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems. However, addressing complex questions, the answers to which are spread across multiple documents, remains a challenging problem. Recent QA systems that are designed to handle complex questions work either on the basis of knowledge graphs, or utilise contem- porary neural models that are expensive to train, in terms of both computational resources and the volume of training data required. In this paper, we present LiCQA, an unsupervised question answer- ing model that works primarily on the basis of corpus evidence. We empirically compare the effectiveness and efficiency of LiCQA with two recently presented QA systems, which are based on different underlying principles. The results of our experiments show that LiCQA significantly outperforms these two state-of-the-art systems on benchmark data with noteworthy reduction in latency.